# supermemoryai/markdowner

A fast tool to convert any website into LLM-ready markdown data. Built by https://supermemory.ai

Repository: https://github.com/supermemoryai/markdowner
Canonical: https://ross.abutalabs.com/products/markdowner
Homepage: https://md.dhr.wtf
Language: TypeScript
License: MIT
License Family: permissive
Last push: 2024-07-21T04:03:59+00:00

## Health v2 (maintenance only)
Score: 24/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 0, release rhythm 35, longevity 60
- inputs: {"age_days": 846, "days_push": 773, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1999, forks 145 (observed 2026-08-28T04:06:03.745720+00:00)

## What it is
Markdowner is a fast web service that converts any website into LLM-ready markdown, with optional LLM filtering, detailed responses, and automatic subpage crawling. It runs on Cloudflare Workers with browser rendering and Durable Objects, and can be self-hosted.

## Use cases
- convert a webpage to markdown for LLM ingestion
- scrape website content into clean markdown
- crawl subpages and get markdown for each
- filter out boilerplate from web pages before feeding to an LLM
- self-host an alternative to r.jina.ai or firecrawl
- get JSON or plain text extraction of a URL

## When to choose
- you need LLM-ready markdown from URLs at low cost
- you want a self-hostable alternative to proprietary scraping APIs
- you need automatic subpage crawling without a sitemap

## When to avoid
- you need heavy-duty large-scale scraping with proxies and JS-heavy sites at scale
- you cannot use Cloudflare Workers paid plan for self-hosting
- you need structured data extraction beyond markdown

## Facets
- artifact type: service
- maturity: active
- function: web-scraping, http-server, nlp, llm-inference
- domain: large-language-models, web-development, crawlers, developer-tools
- platform: cloud, self-hosted
- tags: html-to-markdown, cloudflare-workers, llm-ready-data, turndown, crawler, api, web-server, nodejs

## Member repositories
- supermemoryai/markdowner (main) score 24

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:06:03.745720+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T03:02:11.361647+00:00, confidence not recorded.
  - readme: https://github.com/supermemoryai/markdowner (fetched 2026-08-28T04:06:03.745720+00:00, sha a2347db98817)
  - homepage: https://md.dhr.wtf (fetched 2026-08-29T10:42:10.920349+00:00, sha e82645fc1940)
- Data as of 2026-08-30T08:39:29.467469+00:00.